Classified perceptual coding with adaptive quantization

Abstract

A new technique of adaptively classifying the scene content of an image block has been developed in the proposed perceptual coder. It measures the texture masking energy of an image block and classifies it into one of four perceptual classes: flat, edge, texture, and fine-texture. Each class has an associated factor to adapt the quantizer with the aim of achieving constant quality across an image. A second feature of the perceptual coder is the visual thresholding, a process that reduces bit rate by discarding subthreshold discrete cosine transform (DCT) coefficients without degrading the image perceived quality. Finally, further quality gain is achieved by an improved reference model 8 (RM8) intramode decision, which removes sticking noise artifacts from newly uncovered background found in H.261 coded sequences. Subjective viewing tests, guided by Rec. 500-5, were conducted with 30 subjects. Subjective results confirm the efficacy of the proposed classified coder over the RMS based H.261 coder in two ways: (i) it consistently produces better quality sequences (with a mean opinion score, MOS, of approximately 2.0) when comparing at any fix bit rate; and (ii) it achieves a bit rate saving of 35% when measuring at the same picture quality (i.e., same MOS).